This is done by a script [2] using RedBaron [1], a tool designed for doing
code refactoring. All "default" values are decided by the script and are
strongly consistent with the existing code.
There are 2 changes done manually to fix tests:
[warn] mercurial/exchange.py: experimental.bundle2-output-capture: default needs manual removal
[warn] mercurial/localrepo.py: experimental.hook-track-tags: default needs manual removal
Since RedBaron is not confident about how to indent things [2].
[1]: https://github.com/PyCQA/redbaron
[2]: https://github.com/PyCQA/redbaron/issues/100
[3]:
#!/usr/bin/env python
# codemod_configitems.py - codemod tool to fill configitems
#
# Copyright 2017 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function
import os
import sys
import redbaron
def readpath(path):
with open(path) as f:
return f.read()
def writepath(path, content):
with open(path, 'w') as f:
f.write(content)
_configmethods = {'config', 'configbool', 'configint', 'configbytes',
'configlist', 'configdate'}
def extractstring(rnode):
"""get the string from a RedBaron string or call_argument node"""
while rnode.type != 'string':
rnode = rnode.value
return rnode.value[1:-1] # unquote, "'str'" -> "str"
def uiconfigitems(red):
"""match *.ui.config* pattern, yield (node, method, args, section, name)"""
for node in red.find_all('atomtrailers'):
entry = None
try:
obj = node[-3].value
method = node[-2].value
args = node[-1]
section = args[0].value
name = args[1].value
if (obj in ('ui', 'self') and method in _configmethods
and section.type == 'string' and name.type == 'string'):
entry = (node, method, args, extractstring(section),
extractstring(name))
except Exception:
pass
else:
if entry:
yield entry
def coreconfigitems(red):
"""match coreconfigitem(...) pattern, yield (node, args, section, name)"""
for node in red.find_all('atomtrailers'):
entry = None
try:
args = node[1]
section = args[0].value
name = args[1].value
if (node[0].value == 'coreconfigitem' and section.type == 'string'
and name.type == 'string'):
entry = (node, args, extractstring(section),
extractstring(name))
except Exception:
pass
else:
if entry:
yield entry
def registercoreconfig(cfgred, section, name, defaultrepr):
"""insert coreconfigitem to cfgred AST
section and name are plain string, defaultrepr is a string
"""
# find a place to insert the "coreconfigitem" item
entries = list(coreconfigitems(cfgred))
for node, args, nodesection, nodename in reversed(entries):
if (nodesection, nodename) < (section, name):
# insert after this entry
node.insert_after(
'coreconfigitem(%r, %r,\n'
' default=%s,\n'
')' % (section, name, defaultrepr))
return
def main(argv):
if not argv:
print('Usage: codemod_configitems.py FILES\n'
'For example, FILES could be "{hgext,mercurial}/*/**.py"')
dirname = os.path.dirname
reporoot = dirname(dirname(dirname(os.path.abspath(__file__))))
# register configitems to this destination
cfgpath = os.path.join(reporoot, 'mercurial', 'configitems.py')
cfgred = redbaron.RedBaron(readpath(cfgpath))
# state about what to do
registered = set((s, n) for n, a, s, n in coreconfigitems(cfgred))
toregister = {} # {(section, name): defaultrepr}
coreconfigs = set() # {(section, name)}, whether it's used in core
# first loop: scan all files before taking any action
for i, path in enumerate(argv):
print('(%d/%d) scanning %s' % (i + 1, len(argv), path))
iscore = ('mercurial' in path) and ('hgext' not in path)
red = redbaron.RedBaron(readpath(path))
# find all repo.ui.config* and ui.config* calls, and collect their
# section, name and default value information.
for node, method, args, section, name in uiconfigitems(red):
if section == 'web':
# [web] section has some weirdness, ignore them for now
continue
defaultrepr = None
key = (section, name)
if len(args) == 2:
if key in registered:
continue
if method == 'configlist':
defaultrepr = 'list'
elif method == 'configbool':
defaultrepr = 'False'
else:
defaultrepr = 'None'
elif len(args) >= 3 and (args[2].target is None or
args[2].target.value == 'default'):
# try to understand the "default" value
dnode = args[2].value
if dnode.type == 'name':
if dnode.value in {'None', 'True', 'False'}:
defaultrepr = dnode.value
elif dnode.type == 'string':
defaultrepr = repr(dnode.value[1:-1])
elif dnode.type in ('int', 'float'):
defaultrepr = dnode.value
# inconsistent default
if key in toregister and toregister[key] != defaultrepr:
defaultrepr = None
# interesting to rewrite
if key not in registered:
if defaultrepr is None:
print('[note] %s: %s.%s: unsupported default'
% (path, section, name))
registered.add(key) # skip checking it again
else:
toregister[key] = defaultrepr
if iscore:
coreconfigs.add(key)
# second loop: rewrite files given "toregister" result
for path in argv:
# reconstruct redbaron - trade CPU for memory
red = redbaron.RedBaron(readpath(path))
changed = False
for node, method, args, section, name in uiconfigitems(red):
key = (section, name)
defaultrepr = toregister.get(key)
if defaultrepr is None or key not in coreconfigs:
continue
if len(args) >= 3 and (args[2].target is None or
args[2].target.value == 'default'):
try:
del args[2]
changed = True
except Exception:
# redbaron fails to do the rewrite due to indentation
# see https://github.com/PyCQA/redbaron/issues/100
print('[warn] %s: %s.%s: default needs manual removal'
% (path, section, name))
if key not in registered:
print('registering %s.%s' % (section, name))
registercoreconfig(cfgred, section, name, defaultrepr)
registered.add(key)
if changed:
print('updating %s' % path)
writepath(path, red.dumps())
if toregister:
print('updating configitems.py')
writepath(cfgpath, cfgred.dumps())
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
The ignore regular expression has been updated to detect
"inconsistent config." If present, we track which configs have
that set and we suppress the conflicting defaults error for those
options.
I also added named groups to the regexp to aid readability.
A comment was added to profiling.py to make a desired inconsistent
value error go away.
Changeset 3d003a7a1a87 change 'configwith' behavior so that the default value is
run through the conversion function. In parallel a new user of 'configwith' got
introduced unaware of this coming behavior change. This broke profiling.
We resolve the situation by having the new conversion function cope with a
default value already using the right type.
statprof.display_hotpath() accepts a "limit" function to choose the
minimum threshold for samples to display. The default is 0.05, which
means you don't need individual items contributing less than 5%.
I had a need to adjust this threshold. We already have a config
option for it. So let's reuse it.
check-config.py doesn't like having multiple defaults for the
ui.configwith() calls. The behavior is obviously correct. I'm
not sure if it is worth teaching check-config.py how to ignore
this. So I've just accepted the new output.
Context manager has a mechanism to control extension propagation. It is not
used by profiling right now, but making the code correct will help prevent bug
in the future.
There are no way for this to happen today, but better be safe than sorry, no
one know how the code will evolve. We now make sure the file pointer is closed
even is profiler is None.
It seems sufficiently simple to use "profile(enabled=X)" to not justify having
a dedicated context manager just to read the config.
(I do not have a too strong opinion about this).
This is a step toward allowing context where the profiling in enabled
withing the context range.
This also open the way to kill the dedicated "maybeprofile" context manager
and keep only one of 'profile' and 'maybeprofile'.
The start method is doing all profiler setup and activation. It is currently
unconditionally called by '__init__' but this will be made more flexible in
later changesets.
So far we have been able to use a simple decorator for this. However using the
current context manager makes the scope of the profiling in dispatch
constrainted and the time frame to decide to enable profiling quite limited
(using "maybeprofile")
This is the first step toward the ability to enable the profiling from within
the profiling scope. eg::
with maybeprofiling(ui) as profiler:
...
bar.foo():
...
if options['profile']:
profiler.start()
...
fooz()
...
My target usecase is adding support for "--profile" to alias definitions with
effect. These are to be used with "profiling.output=blackbox" to gather data
about operation that get slow from time to time (eg: pull being minutes instead
of seconds from time to time).
Of course, in such case, the scope of the profiling would be smaller since
profiler would be started after running extensions 'reposetup' (and other
potentially costly logic), but these are not relevant for my target usecase
(multiple second commits, multiple tens of seconds pull).
Currently adding '--profile' to a command through alias requires to re-spin a
Mercurial binary (using "!$HG" in alias), which as a significant performance
impact, especially in context where startup performance is being worked on...
An alternative approach would be to stop using the context manager in dispatch
and move back to a try/finally setup.
459366b580cf makes profiler start early without loading extensions. That
makes it impossible for an extension to add customized profilers.
This patch adds a special case: if a profiler is not found but an extension
with the same name could be loaded, load that extension first, and expect it
to have a "profile" contextmanager method. This allows customized profilers
and extension setup time is still profiled.
We synthesize function call begin/end events from snapshots, and
try (configurably) to eliminate "noisy" stack frames.
Example invocation:
hg --config profiling.output=$HOME/Desktop/clone.json \
--config profiling.statformat=chrome \
--profile clone https://www.mercurial-scm.org/repo/hg
pycompat.getenv returns os.getenvb on py3 which is not available on Windows.
This patch replaces them with encoding.environ.get and checks to ensure no
new instances of os.getenv or os.setenv are introduced.
os.getenv deals with unicodes on Python 3, so we have pycompat.osgetenv to
deal with bytes. This patch replaces occurrences on os.getenv with
pycompat.osgetenv
The statprof sampling profiler runs with significantly less overhead.
Its data is therefore more useful. Furthermore, its default output
shows the hotpath by default, which I've found to be way more useful
than the default profiler's function time table.
There is one behavioral regression with this change worth noting:
the statprof profiler currently doesn't profile individual hgweb
requests like lsprof does. This is because the current implementation
of statprof only profiles the thread that started profiling.
The ability for lsprof to profile individual hgweb requests is
relatively new and likely not widely used. Furthermore, I have plans
to modify statprof to support profiling multiple threads. I expect
that change to go through several iterations. I'm submitting this
patch first so there is more time to test statprof. Perfect is the
enemy of good.
Now that the statprof module is vendored and suitable for use, we
switch our statprof profiler to use it. This required some minor
changes because of drift between the official statprof profiler
and the vendored copy.
We also incorporate Facebook's improvements from the "statprofext"
extension at
https://bitbucket.org/facebook/hg-experimental, notably support for
different display formats.
Because statprof output is different, this is marked as BC. Although
most users likely won't notice since most users don't profile.
And refactor dispatch.py to use it. As you can see, the resulting code
is much simpler.
I was tempted to inline _runcommand as part of writing this series.
However, a number of extensions wrap _runcommand. So keeping it around
is necessary (extensions can't easily wrap runcommand because it calls
hooks before and after command execution).
This makes profiling more flexible since we can now call multiple
functions when a profiler is active. But the real reason for this
is to enable a future consumer to profile a function that returns
a generator. We can't do this from the profiling function itself
because functions can either be generators or have return values:
they can't be both. So therefore it isn't possible to have a generic
profiling function that can both consume and re-emit a generator
and return a value.
Currently, profiling code lives in dispatch.py, which is a low-level
module centered around command dispatch. Furthermore, dispatch.py
imports a lot of other modules, meaning that importing dispatch.py
to get at profiling functionality would often result in a module import
cycle.
Profiling is a generic activity. It shouldn't be limited to command
dispatch. This patch moves profiling code from dispatch.py to the
new profiling.py. The low-level "run a profiler against a function"
functions have been moved verbatim. The code for determining how to
invoke the profiler has been extracted to its own function.
I decided to create a new module rather than stick this code
elsewhere (such as util.py) because util.py is already quite large.
And, I foresee this file growing larger once Facebook's profiling
enhancements get added to it.
